© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 1672
    Prev
    Next
    INDEX
    Explanations

    variations of the word "a" and assess their significance in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.40
    1.8%
    1967
    +0.18
    0.8%
    1984
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1984
    +0.40
    0.10
    1034
    +0.18
    0.08
    1896
    +0.12
    0.07
    Negative Logits
    <bos>
    -2.46
    ⓧ
    -0.69
    //};
    -0.67
     préfère
    -0.64
    };*/
    -0.62
    endfor
    -0.59
    {?>
    -0.58
    //});
    -0.57
     découvre
    -0.56
     croit
    -0.55
    POSITIVE LOGITS
     conflic
    0.90
     marea
    0.86
     Compañ
    0.83
     viciss
    0.83
    ">...
    0.82
     Haci
    0.82
    Ehh
    0.81
     zove
    0.77
     farmacia
    0.76
     valencia
    0.76
    Activations Density 0.558%

    No Known Activations